English

Subadditivity of Matrix phi-Entropy and Concentration of Random Matrices

Information Theory 2014-04-29 v1 math.IT Probability

Abstract

Matrix concentration inequalities provide a direct way to bound the typical spectral norm of a random matrix. The methods for establishing these results often parallel classical arguments, such as the Laplace transform method. This work develops a matrix extension of the entropy method, and it applies these ideas to obtain some matrix concentration inequalities.

Keywords

Cite

@article{arxiv.1308.2952,
  title  = {Subadditivity of Matrix phi-Entropy and Concentration of Random Matrices},
  author = {Joel A. Tropp and Richard Y. Chen},
  journal= {arXiv preprint arXiv:1308.2952},
  year   = {2014}
}

Comments

23 pages